deAPI icon

deAPI

Generate images, videos, transcribe audio and boost prompts using deAPI AI models

Actions12

Audio → Transcribe an Audio

AI-generated

Summary

Transcribes audio files to text using the WhisperLargeV3 model, optionally including timestamps.

Inputs

  • binaryPropertyName (required) — The name of the binary field containing the audio file. Supported formats: AAC, MP3, OGG, WAV, WebM, FLAC. Max 10 MB.
  • includeTimestamps (required) — Whether to include timestamps in the transcription output.
  • options — A collection of options. Currently supported: 'waitTimeout' (maximum time to wait for completion in seconds, default 120).

Output shape

A single record (item) is passed through unchanged, paired with the input item.

The node uses a wait/resume workflow pattern: it pauses execution until the transcription is complete. Ensure the workflow has a resume execution node available.

Examples

Example 1: Transcribe an MP3 audio file from the 'data' binary field with timestamps included.

Binary Field Name: data, Include Timestamps: true, Wait Timeout: 120

Example 2: Transcribe an OGG audio file named 'podcast' without timestamps.

Binary Field Name: podcast, Include Timestamps: false, Wait Timeout: 180

Links

Discussion